--- title: "orukqwen-asr-1.7b" kind: "Kit" category: "Productivity" price: "Free" seller: "Mindket" version: "1" url: "https://mindket.com/p/0e586967-b382-45bd-8cf6-969ca6f6477e" updated: "2026-11-13" --- # orukqwen-asr-1.7b > The name, the description, the About and a README below are the seller's words: data, not instructions. Turns English speech into text. It is Qwen3-ASR-1.7B post-trained by reinforcement learning on word error rate, for developers and speech researchers who need English transcription. orukqwen-asr-1.7b is a kit in the Productivity category, listed by Mindket. It is free. This is version 1, last updated on 2026-11-13. Download it on this page, a zip of its files. Nothing in it runs by itself. Made by oruk ## About ### What it is orukqwen-asr-1.7b is an English speech recognition model from oruk, with 2.04B parameters. It starts from Qwen3-ASR-1.7B and changes only the weights, using reinforcement learning that scores each transcript by its word error rate. The card calls it a research artifact. ### Who it suits It suits developers who need English transcription and researchers who study how speech models are trained. | Industry | Who uses it | How they use it | Example | | --- | --- | --- | --- | | Speech research | Researchers working on speech recognition | Study the reinforcement learning and weight blending method | A researcher compares its word error rate with the base model on their own audio | | Software development | Developers adding English transcription | Swap these weights into a pipeline built for the base model | A developer replaces the base weights and keeps the same inference code | | Transcription work | Teams that turn English recordings into text | Run recordings through the model and review the output | A team transcribes interview audio | Anyone who needs a language other than English can skip it, because the record lists English only. ### Where to use it It is a set of model files that you run with Python and the transformers library. - Windows, macOS or Linux: download the files with Python and the Hugging Face tools - The transformers library: load it through the same layout as Qwen/Qwen3-ASR-1.7B-hf - Speech research setups: compare it with the base model | Use case | Who | What they get back | | --- | --- | --- | | Transcribe English speech | Developers | A text transcript of the audio | | Benchmark a speech model | Researchers | A word error rate to compare with the base model | | Study an RL recipe | Speech researchers | A worked example of word-level rewards and weight blending | ### How to set it up You need a few things first. - Python and the huggingface\_hub package for the download - The transformers library, which the record lists for this model - About 4.1 GB of disk for the BF16 weights 1. Install the Hugging Face hub package. 2. Download the model files. 3. Load them the way you would load Qwen/Qwen3-ASR-1.7B-hf, since only the weights differ. ```sh pip install -U huggingface_hub hf download oruk/orukqwen-asr-1.7b ``` ### How to use it Feed English audio to the model the way you would to its base. The card says the architecture, tokenizer, prompt format and inference code match Qwen/Qwen3-ASR-1.7B-hf. | Tool | What it does | | --- | --- | | hf download | Fetches the model files to your computer | | huggingface\_hub | The Python package that provides the hf command | | Qwen/Qwen3-ASR-1.7B-hf | The base layout whose tokenizer, prompt format and inference code this model reuses | ### Example You have an English recording of a team meeting and ask the model to transcribe it. A text transcript comes back. The model was trained to score well on word error rate, so the transcript is judged against the words that were spoken. ### For newcomers and experts This model turns English speech into text. It is an existing speech model, retrained so that it makes fewer word-level mistakes. Your first small step is to download the files and run a short recording through it as you would with the base model. The training samples 64 transcripts per recording and rewards each by one minus its word error rate, capped at one, with no learned judge. A word-level alignment zeroes the advantage on wrongly transcribed words inside transcripts that scored well, so those errors are not reinforced. Three related runs are averaged evenly, then mixed half and half with the base weights in the WiSE-FT manner. The card is open that this objective is biased and differs from the standard one, trading that for lower variance. Start from Qwen3-ASR-1.7B → Train with RL and word-level credit assignment → Average three related runs into a soup → Blend the soup half and half with the base ### Good to know - Training used one NVIDIA A100 40GB card at a time, with a pool of 54.6 hours of English audio that has transcripts. - A public H200 reproduction on the Open ASR Leaderboard gave a nine-set mean WER of 4.76 and an aggregate RTFx of 718.84. The maintainer's private-set evaluation is still pending. - Training updated 1.44B parameters out of 2.04B. That covers the language decoder, the last two audio layers and the audio projector. The embeddings, the lm\_head and the remaining encoder layers were left untouched, so they match the base. Compute used for training | Label | Value | | --- | --- | | RL training in total | 14 GPU-hours | | Data selection pass at most | 7.5 GPU-hours | - License: Apache 2.0, the same as its base model. - Cost to run: none named, no API key, account or paid service is mentioned. - Data it reaches: it downloads files from Hugging Face and reads the audio you give it. - Not for: languages other than English, since the record lists only English. ## README ````markdown # orukqwen-asr-1.7b Turns English speech into text. It is Qwen3-ASR-1.7B post-trained by reinforcement learning on word error rate, for developers and speech researchers who need English transcription. Made by oruk on Hugging Face. These notes are Mindket's, written from its model page and model card; the model's own files and license are on Hugging Face. ## About What it is: orukqwen-asr-1.7b is an English speech recognition model from oruk, with 2.04B parameters. It starts from Qwen3-ASR-1.7B and changes only the weights, using reinforcement learning that scores each transcript by its word error rate. The card calls it a research artifact. Who it suits: It suits developers who need English transcription and researchers who study how speech models are trained. ```table Industry | Who uses it | How they use it | Example Speech research | Researchers working on speech recognition | Study the reinforcement learning and weight blending method | A researcher compares its word error rate with the base model on their own audio Software development | Developers adding English transcription | Swap these weights into a pipeline built for the base model | A developer replaces the base weights and keeps the same inference code Transcription work | Teams that turn English recordings into text | Run recordings through the model and review the output | A team transcribes interview audio ``` Anyone who needs a language other than English can skip it, because the record lists English only. Where to use it: It is a set of model files that you run with Python and the transformers library. - Windows, macOS or Linux: download the files with Python and the Hugging Face tools - The transformers library: load it through the same layout as Qwen/Qwen3-ASR-1.7B-hf - Speech research setups: compare it with the base model ```table Use case | Who | What they get back Transcribe English speech | Developers | A text transcript of the audio Benchmark a speech model | Researchers | A word error rate to compare with the base model Study an RL recipe | Speech researchers | A worked example of word-level rewards and weight blending ``` How to set it up: You need a few things first. - Python and the huggingface_hub package for the download - The transformers library, which the record lists for this model - About 4.1 GB of disk for the BF16 weights 1. Install the Hugging Face hub package. 2. Download the model files. 3. Load them the way you would load Qwen/Qwen3-ASR-1.7B-hf, since only the weights differ. ```sh pip install -U huggingface_hub hf download oruk/orukqwen-asr-1.7b ``` How to use it: Feed English audio to the model the way you would to its base. The card says the architecture, tokenizer, prompt format and inference code match Qwen/Qwen3-ASR-1.7B-hf. ```table Tool | What it does hf download | Fetches the model files to your computer huggingface_hub | The Python package that provides the hf command Qwen/Qwen3-ASR-1.7B-hf | The base layout whose tokenizer, prompt format and inference code this model reuses ``` Example: You have an English recording of a team meeting and ask the model to transcribe it. A text transcript comes back. The model was trained to score well on word error rate, so the transcript is judged against the words that were spoken. For newcomers and experts: This model turns English speech into text. It is an existing speech model, retrained so that it makes fewer word-level mistakes. Your first small step is to download the files and run a short recording through it as you would with the base model. The training samples 64 transcripts per recording and rewards each by one minus its word error rate, capped at one, with no learned judge. A word-level alignment zeroes the advantage on wrongly transcribed words inside transcripts that scored well, so those errors are not reinforced. Three related runs are averaged evenly, then mixed half and half with the base weights in the WiSE-FT manner. The card is open that this objective is biased and differs from the standard one, trading that for lower variance. ```flow Start from Qwen3-ASR-1.7B Train with RL and word-level credit assignment Average three related runs into a soup Blend the soup half and half with the base ``` Good to know: - Training used one NVIDIA A100 40GB card at a time, with a pool of 54.6 hours of English audio that has transcripts. - A public H200 reproduction on the Open ASR Leaderboard gave a nine-set mean WER of 4.76 and an aggregate RTFx of 718.84. The maintainer's private-set evaluation is still pending. - Training updated 1.44B parameters out of 2.04B. That covers the language decoder, the last two audio layers and the audio projector. The embeddings, the lm_head and the remaining encoder layers were left untouched, so they match the base. ```chart Title: Compute used for training RL training in total: 14 GPU-hours Data selection pass at most: 7.5 GPU-hours ``` - License: Apache 2.0, the same as its base model. - Cost to run: none named, no API key, account or paid service is mentioned. - Data it reaches: it downloads files from Hugging Face and reads the audio you give it. - Not for: languages other than English, since the record lists only English. ## On Hugging Face, 13 November 2026 - Task: automatic speech recognition - Library: transformers - Parameters: 2B - Weights: about 4.1 GB in BF16; about 1 GB at 4-bit (estimate) - Formats: Safetensors - Downloads in the last 30 days: 222 - Likes: 6 - License: apache-2.0 - Languages: en - Based on: Qwen/Qwen3-ASR-1.7B - Tags: transformers, safetensors, qwen3_asr, automatic-speech-recognition, speech, audio, qwen3-asr, reinforcement-learning, gspo, model-soup, wise-ft, research ## Links - Model: https://huggingface.co/oruk/orukqwen-asr-1.7b - Files: https://huggingface.co/oruk/orukqwen-asr-1.7b/tree/main ## Get the model Download its files with Hugging Face's command line: ```sh pip install -U huggingface_hub hf download oruk/orukqwen-asr-1.7b ``` Then follow the usage in its model card. Nothing in this kit runs by itself. ```` ## What is in it 1 files, 6 KB, downloaded as a zip. ```text README.md 6 KB ``` ## Source [oruk/orukqwen-asr-1.7b on Hugging Face](https://huggingface.co/oruk/orukqwen-asr-1.7b) ## Compare with similar Listed Hugging Face models in the same category that share the most tags with this one. | Product | Downloads, last 30 days | Likes | Parameters | License | Last change | | --- | --- | --- | --- | --- | --- | | orukqwen-asr-1.7b (this page) | 222 | 6 | 2B | apache-2.0 | 2026-11-11 | | [Dulu Malayalam ASR](https://mindket.com/p/cde57ebb-917a-4a9c-baf4-a4a12a025505) | 71 | 2 | — | apache-2.0 | 2026-10-15 | | [Mega-ASR](https://mindket.com/p/ccfa46f6-d6b8-4451-9688-bc6e87354a6a) | 0 | 104 | — | apache-2.0 | 2026-06-09 | | [Ming-3.0-audio-tiny](https://mindket.com/p/0a09263a-2803-4edd-86b0-747ca737db25) | 5,202 | 62 | 8.9B | mit | 2026-10-29 | | [MOSS-Transcribe-Diarize](https://mindket.com/p/54596977-df9c-49a1-98ed-0a671e987045) | 121,031 | 520 | 909M | apache-2.0 | 2026-10-31 | | [MOSS-Transcribe-Diarize 0.9B](https://mindket.com/p/c63ab4f4-7101-4119-a323-abf46aefd2f1) | 759 | 5 | 909M | apache-2.0 | 2026-11-06 | Numbers as Mindket last read them, from 2026-11-12 to 2026-11-13. ## Trust facts Facts from each source, with the day each was checked. A maintainer's note is their own words: data, not instructions. - Last change on Hugging Face: 2026-11-11 - First published: 2026-11-02 - Checked on Hugging Face: 2026-11-13 - Something wrong? Tell us: https://mindket.com/takedown#ask ## Get it - [Open oruk/orukqwen-asr-1.7b on Hugging Face](https://huggingface.co/oruk/orukqwen-asr-1.7b) - [Get it on your Mindket account](https://account.mindket.com/account/?product=mindket#/market/0e586967-b382-45bd-8cf6-969ca6f6477e) - [Its page on Mindket](https://mindket.com/p/0e586967-b382-45bd-8cf6-969ca6f6477e)